Select a calendar:
Filter April Events by Event Type:
Events for April 19, 2017
Wed, Apr 19, 2017 @ 10:30 AM - 12:30 PM
PhD Candidate: Koki Nagano
Committee: Paul Debevec (CS, chair), Hao Li (CS), Jernej Barbic (CS), Aiichiro Nakano (CS), Michelle Povinelli (EE)
Title: Multi-scale Dynamic Capture for High Quality Digital Humans
Time: April 19 (Wednesday) 10:30-12:30pm
Room: KAP 164
Digitally creating a virtual human indistinguishable from a real human has been one of the central goals of Computer Graphics, Human-Computer Interaction, and Artificial Intelligence. Such digital characters are not only the primary creative vessel for immersive storytellers and filmmakers, but also a key technology to understand the process of how humans think, see, and communicate in the social environment. In order for digital character creation techniques to be valuable in simulating and understanding humans, the hardest challenge is for them to appear believably realistic from any point of view in any environment, and to behave and interact in a convincing manner.
Creating a photorealistic rendering of a digital avatar is increasingly more accessible due to rapid advancement in sensing technologies and rendering techniques. However, generating realistic movement and dynamic details that are compatible with such a photorealistic appearance still relies on manual work from experts, which hinders the potential impact of digital avatar technologies in real world applications. Generating dynamic details is especially important for facial animation, as humans are extremely tuned to sense people's intentions from facial expressions.
In this dissertation, we propose systems and approaches for capturing the appearance and motion to reproduce high fidelity digital avatars that are rich in subtle motion and appearance details. We aim for a framework which can generate consistent dynamic detail and motion at the resolution of skin pores and fine wrinkles, and can provide extremely high resolution microstructure deformation for use in cinematic storytelling or immersive virtual reality environments.
This thesis presents three principal techniques for achieving multi-scale dynamic capture for digital humans. The first is a multi-view capture system and a stereo reconstruction technique which directly produces a complete high-fidelity head model with consistent facial mesh topology. Our method jointly solves for stereo constraints and consistent mesh parameterization from static scans or a dynamic performance, producing dense correspondences on an artist quality template. Additionally, we propose a technique to add dynamic per-frame high and middle frequency details from the flat-lit performance video. Second, we propose a technique to estimate high fidelity 3D scene flow from multiview video. The motion estimation fully respects high quality data from multiview input, and can be incorporated to any facial performance capture pipeline to improve the fidelity of the facial motion. Since the motion can be estimated without relying on any domain-specific priors or regularization, our method scales well to modern systems with many high-resolution cameras. Third, we present a technique to synthesize dynamic skin microstructure details to produce convincing facial animation. We measure and quantify how skin microstructure deformation contributes to dynamic skin appearance, and present an efficient way to simulate dynamic skin microstructure. When combined with the state-of-the art performance capture and face scanning techniques, it can significantly improve the realism of animated faces for virtual reality, video games, and visual effects.
Location: Kaprielian Hall (KAP) - 164
Audiences: Everyone Is Invited
Contact: Lizsl De Leon
Wed, Apr 19, 2017 @ 12:00 PM - 02:00 PM
Receptions & Special Events
Bi-Weekly regular faculty meeting for invited full-time Computer Science faculty only. Event details emailed directly to attendees.
Audiences: Invited Faculty Only
Contact: Assistant to CS chair
Wed, Apr 19, 2017 @ 03:30 PM - 04:30 PM
Aerospace and Mechanical Engineering
Conferences, Lectures, & Seminars
Speaker: Ilenia Battiato, Assistant Professor of Energy Resources Engineering at Stanford University
Talk Title: Transport Phenomena over Patterned Surfaces
Abstract: Coupled flows over patterned surfaces occur in a variety of natural phenomena, biological systems and industrial processes. Some example includes bioreactors, micro- and nano-patterned water filtration membranes, superhydrophobic ridges surfaces, and submerged vegetation, just to mention a few. Designing and optimizing the topology of the structure to achieve target performance at the system-scale (or macroscale) is still an open question since fully resolved numerical simulations are too prohibitive when a great disparity of scales between the pattern and the device exists. By treating the patterned surface as a permeable layer, we formulate a system of coupled Navier-Stokes/Brinkman equations, which is amenable of analytical solution for the mean filtration velocity inside the pattern, and allows one to uncover and quantify the relationship between microstructure and macroscopic response. We employ this effective-medium framework to model a number of physical systems including channel turbulent flows over arrays of carbon nanotubes, superhydrophobic ridged surfaces, and submerged vegetation. We finally investigate the appropriateness of treating the pattern as a porous medium by conducting experiments in microfluidic channels with controlled microtexture.
Biography: Dr. Battiato received her MSc. In Engineering Physics in 2008 and a Ph.D. in Engineering Science with a specialization in Computational Sciences from the Mechanical and Aerospace Engineering department at the University of California San Diego in 2010. She did her postdoctoral training in Theoretical Physics at the Max Planck Institute for Dynamics and Self-Organization in Goettingen, Germany. In 2012 she joined the Mechanical Engineering Department at Clemson University as assistant professor and then in 2014 the Mechanical Engineering Department at SDSU. In 2016, she moved to the department of Energy Resources Engineering at Stanford University. Her research interests lie in theoretical/computational fluid mechanics and transport processes in porous media, multiscale and hybrid computational methods, effective medium theories, and multiphase flows. In 2015 she was awarded of the Department of Energy Young Investigator award in Basic Energy Sciences for her work on multiscale models of reactive transport in the subsurface.
Host: Department of Aerospace and Mechanical Engineering
More Info: https://ame.usc.edu/about/seminars/
Location: Seaver Science Library (SSL) - 150
Audiences: Everyone Is Invited
Contact: Ashleen Knutsen